Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/non-destructive/closed-world, so safety is covered; the description adds the valuable part — that state is carried via `_meta.investigation_id` across later calls and is finalized by investigation_close into a "Veredicto markdown" artifact. Slight tension remains: "Start" implies creating session state while readOnlyHint=true, though this is not a hard contradiction since nothing is described as mutated or destroyed. It does not say whether re-opening with the same context resumes or replaces an existing session.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, roughly thirty words, front-loaded with the purpose before the follow-up mechanics. Every clause carries actionable information about lifecycle or next steps.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need no explanation, and all six optional parameters are schema-documented. What is missing is prerequisite context — whether an active work context (context_id / ops_context_open) is expected, and how the session interacts with those sibling context tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so env/query/hostname/context_id/service_hints/include_memory_precedents are already fully documented and the baseline of 3 applies. The description adds a non-schema parameter (`_meta.investigation_id`) and its propagation rule, but says nothing about which of these six inputs shape the session scope versus merely seed hypotheses.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Start a scoped MCP investigation") and names the terminating sibling (investigation_close), so the agent knows this opens a session rather than running a query. What "scoped" actually means for the investigation is never defined.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit workflow: call this first, propagate `_meta.investigation_id` on subsequent atomic tool calls, then finish with investigation_close. It does not say when NOT to open an investigation, nor how this differs from the similar session-opening siblings ops_context_open / ops_set_work_context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.